Skip to main content
Glama

playtest_run

Play a web game (URL or ZIP build) as on a PC and as on a weak phone: errors, missing files, black or frozen screen, load time, draw calls, textures, shader stalls, memory leaks, build weight, video and screenshots. Price: $0.25 USDC via x402, charged only on success. Part of Playtest: Plays a web game in a real browser, as on a PC and as on a weak phone, and reports what an agent needs to fix: errors, missing files, a black or frozen screen, load time, draw calls, texture memory, shader stalls, memory leaks and build weight, with a video and screenshots of each pass.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "playtest_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic URL of the game page.
zipNoZIP of a static web build as base64, up to about 35 MB (index.html at the root or one folder down; Unity WebGL builds work). Bigger builds: zipUrl, up to 50 MB.
seedNoRandom input seed, to repeat a run.
stepsNoOptional scenario played first: wait, key, click, tap, type.
monkeyNoAfter the steps, press random keys, clicks and taps until the pass ends.
zipUrlNo
secondsNoPlay time per profile, not counting loading.
profilesNodesktop: 1280x720; phone: 390x844 touch screen with the CPU slowed 4x.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose two non-obvious behaviors: the $0.25 USDC x402 charge and that it bills only on success. What it omits is failure/timeout behavior, what a partial or crashed run returns, and any concurrency or rate constraints on a job that runs two browser profiles for up to 45 seconds each.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The capability list is front-loaded and effective, but the second 'Part of Playtest' paragraph re-enumerates the same diagnostics and outputs almost verbatim, adding bulk without new information. Roughly half the text is redundant with the first paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, no-annotation, no-output-schema tool, the description covers what is measured and what comes back (video plus screenshots per pass) and the cost. It stops short of explaining failure modes, run duration bounds, or how results are delivered, which an agent needs before spending money on a call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 88%, so parameters are already well documented, and the description adds little on top of it — it only restates the desktop/phone profile concept the schema already defines. It does not, for example, explain how `seed` and `monkey` interact to make a run reproducible.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Play a web game (URL or ZIP build) as on a PC and as on a weak phone') plus the exact diagnostics produced (errors, black screen, draw calls, memory leaks, build weight, video/screenshots). No sibling tool covers browser playtesting, so the boundary is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the scenario listing (catching errors, black/frozen screens, perf regressions), but the description never says when to prefer this over alternatives or when a run is warranted. It also gives no guidance on choosing a URL versus an inline ZIP versus zipUrl beyond what the schema already states.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources